{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,3]],"date-time":"2022-04-03T11:01:21Z","timestamp":1648983681279},"reference-count":30,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2017]]},"DOI":"10.1587\/transinf.2016edp7375","type":"journal-article","created":{"date-parts":[[2017,4,30]],"date-time":"2017-04-30T22:14:38Z","timestamp":1493590478000},"page":"1067-1078","source":"Crossref","is-referenced-by-count":1,"title":["LTDE: A Layout Tree Based Approach for Deep Page Data Extraction"],"prefix":"10.1587","volume":"E100.D","author":[{"given":"Jun","family":"ZENG","sequence":"first","affiliation":[{"name":"School of Software Engineering, Chongqing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"LI","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Chongqing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brendan","family":"FLANAGAN","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Electrical Engineering, Kyushu University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sachio","family":"HIROKAWA","sequence":"additional","affiliation":[{"name":"Research Institute for Information Technology, Kyushu University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] C.-H. Chang, M. Kayed, M.R. Girgis, and K.F. Shaalan, \u201cA Survey of Web Information Extraction Systems,\u201d IEEE Trans. Knowl. Data Eng., vol.18, no.10, pp.1411-1428, Oct. 2006.","DOI":"10.1109\/TKDE.2006.152"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] E. Ferrara, P. De Meo, G. Fiumara, and R. Baumgartner, \u201cWeb Data Extraction, Applications and Techniques: A Survey,\u201d Knowledge-Based Systems, vol.70, pp.301-323, 2014.","DOI":"10.1016\/j.knosys.2014.07.007"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] A. Banu and M. Chitra, \u201cDWDE-IR: An Efficient Deep Web Data Extraction for Information Retrieval on Web Mining,\u201d Journal of Emerging Technologies in Web Intelligence, vol.6, no.1, pp.133-141, 2014.","DOI":"10.4304\/jetwi.6.1.133-141"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] N. Anderson and J. Hong, \u201cVisually Extracting Data Records from Query Result Pages,\u201d Web Technologies and Applications, vol.7808, pp.3982-403, 2013.","DOI":"10.1007\/978-3-642-37401-2_40"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] T. Lin, B.H. Qiang, S. Long, and H. Qian, \u201cDeep Web Data Extraction Based on Regular Expression,\u201d Advanced Materials Research, vols.718-720, pp.2242-2247, 2013.","DOI":"10.4028\/www.scientific.net\/AMR.718-720.2242"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] J. Zeng, B. Flanagan, S. Hirokawa, and E. Ito, \u201cA Web Page Segmentation Approach Using Visual Semantics,\u201d IEICE Trans. Inf. & Syst., vol.E97-D, no.2, pp.223-230, Feb. 2014.","DOI":"10.1587\/transinf.E97.D.223"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] W. Thamviset and S. Wongthanavasu, \u201cInformation extraction for deep web using repetitive subject pattern,\u201d World Wide Web, vol.17, Issue 5, pp.1109-1139, 2014.","DOI":"10.1007\/s11280-013-0248-y"},{"key":"8","unstructured":"[8] B.A. Banu and M. Chitra, \u201cA Novel Ensemble Vision Based Deep Web Data Extraction Technique for Web Mining Applications,\u201d IEEE International Conference on Advanced Communication Control and Computing Technologies (ICACCCT 2012), Syed Ammal Engn Coll, Ramanathapuram, INDIA, Aug. 2012, pp.110-114, 2012."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] J. Zeng, T. Sakai, B. Flanagan, and S. Hirokawa, \u201cExtraction of Relevant Components Using Shallow Structure of HTML Documents,\u201d Proc. Int'l Conf. on Fuzzy Systems and Knowledge Discovery (FSKD), pp.1198-1202, 2012.","DOI":"10.1109\/FSKD.2012.6234295"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] L. Bing, W. Lam, and Y. Gu, \u201cTowards a unified solution: data record region detection and segmentation,\u201d Proc. Conf. Information and Knowledge Management (CIKM), pp.1265-1274, 2011.","DOI":"10.1145\/2063576.2063761"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] X. Xie, Y. Fang, Z. Zhang, and L. Li, \u201cExtracting data records from Web using suffix tree,\u201d Proc. ACM SIGKDD Workshop on Mining Data Semantics (MDS), Article no.12, 2012.","DOI":"10.1145\/2350190.2350202"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] W. Liu, X. Meng, and W. Meng, \u201cVide: A vision-based approach for deep Web data extraction,\u201d IEEE Trans. Knowl. Data Eng., vol.22, Issue 3, pp.447-460, 2010.","DOI":"10.1109\/TKDE.2009.109"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] G. Miao, J. Tatemura, W.-P. Hsiung, A. Sawires, and L.E. Moser, \u201cExtracting data records from the Web using tag path clustering,\u201d Proc. the 18th Int'l Conf. on World wide Web (WWW), pp.981-990, 2009.","DOI":"10.1145\/1526709.1526841"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] A. Sahuguet and F. Azavant, \u201cBuilding Intelligent Web Applications Using Lightweight Wrappers,\u201d Data and Knowledge Eng., vol.36, no.3, pp.283-316, 2001.","DOI":"10.1016\/S0169-023X(00)00051-3"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] B. Liu, R.L. Grossman, and Y. Zhai, \u201cMining Data Records in Web Pages,\u201d Proc. Int'l Conf. Knowledge Discovery and Data Mining (KDD), pp.601-606, 2003.","DOI":"10.1145\/956750.956826"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] C.-N. Hsu and M.-T. Dung, \u201cGenerating Finite-State Transducers for Semi-Structured Data Extraction from the Web,\u201d Information Systems, vol.23, no.8, pp.521-538, 1998.","DOI":"10.1016\/S0306-4379(98)00027-1"},{"key":"17","unstructured":"[17] D. Cai, S. Yu, J. Wen, and W. Ma, \u201cVIPS: a visionbased page segmentation algorithm,\u201d Technical Report MSR-TR-2003-79,Microsoft Reseach, 2003."},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] G.O. Arocena and A.O. Mendelzon, \u201cWebOQL: Restructuring Documents, Databases and Webs,\u201d Proc. Int'l Conf. Data Eng. (ICDE), pp.24-33, 1998.","DOI":"10.1109\/ICDE.1998.655754"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] H. Zhao, W. Meng, Z. Wu, V. Raghavan, and C.T. Yu, \u201cFully Automatic Wrapper Generation for Search Engines,\u201d Proc. Int'l World Wide Web Conf. (WWW), pp.66-75, 2005.","DOI":"10.1145\/1060745.1060760"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] I. Muslea, S. Minton, and C.A. Knoblock, \u201cHierarchical Wrapper Induction for Semistructured Information Sources,\u201d Autonomous Agents and Multi-Agent Systems, vol.4, nos.1\/2, pp.93-114, 2001.","DOI":"10.1023\/A:1010022931168"},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] J. Hammer, J. McHugh, and H. Garcia-Molina, \u201cSemistructured Data: The TSIMMIS Experience,\u201d Proc. East-European Workshop Advances in Databases and Information Systems (ADBIS), pp.1-8, 1997.","DOI":"10.14236\/ewic\/ADBIS1997.22"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] K. Simon and G. Lausen, \u201cViPER: Augmenting Automatic Information Extraction with Visual Perceptions,\u201d Proc. Conf. Information and Knowledge Management (CIKM), pp.381-388, 2005.","DOI":"10.1145\/1099554.1099672"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] K. Zhang and D. Shasha, \u201cSimple Fast Algorithms for the Editing Distance between Trees and Related Problems,\u201d SIAM J. COMPUT, vol.18, no.6, pp.1245-1262, 1989.","DOI":"10.1137\/0218082"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] L. Liu, C. Pu, and W. Han, \u201cXWRAP: An XML-Enabled Wrapper Construction System for Web Information Sources,\u201d Proc. Int'l Conf. Data Eng. (ICDE), pp.611-621, 2000.","DOI":"10.1109\/ICDE.2000.839475"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] N. Kushmerick, \u201cWrapper Induction: Efficiency and Expressiveness,\u201d Artificial Intelligence, vol.118, nos.1\/2, pp.15-68, 2000.","DOI":"10.1016\/S0004-3702(99)00100-9"},{"key":"26","unstructured":"[26] P. Xiang, X. Yang, and Y. Shi, \u201cWeb Page Segmentation Based on Gestalt Theory,\u201d Proc. Int'l Conf. on Multimedia and Expo (ICME), pp.2253-2256, 2007."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] V. Crescenzi and G. Mecca, \u201cGrammars Have Exceptions,\u201d Information Systems, vol.23, no.8, pp.539-565, 1998.","DOI":"10.1016\/S0306-4379(98)00028-3"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] Y. Hwang, J. Kim, and E. Seo, \u201cStructure-aware Web transcoding for mobile devices,\u201d IEEE Internet Comput., vol.7, Issue 5,pp.14-21, 2003.","DOI":"10.1109\/MIC.2003.1232513"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] Y. Yamada, N. Craswell, T. Nakatoh, and S. Hirokawa, \u201cTestbed for information extraction from deep Web,\u201d Proc. Int'l World Wide Web conf. on Alternate track papers & posters (WWW Alt), pp.346-347, 2004.","DOI":"10.1145\/1013367.1013468"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] Y. Yang, \u201cAn Evaluation of Statistical Approaches to Text Categorization,\u201d Information Retrieval, vol.1, Issue 1-2, pp.69-90, 1999.","DOI":"10.1023\/A:1009982220290"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/5\/E100.D_2016EDP7375\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T16:45:30Z","timestamp":1602002730000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E100.D\/5\/E100.D_2016EDP7375\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":30,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2017]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2016edp7375","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]}}}